| { | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "<sos>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "3": { | |
| "content": "<eos>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "bos_token": "<sos>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<eos>", | |
| "extra_special_tokens": {}, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<pad>", | |
| "tokenizer_class": "KhmerOCRTokenizer", | |
| "unk_token": "<unk>", | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| "tokenization_khmerocr.KhmerOCRTokenizer", | |
| null | |
| ] | |
| } | |
| } |